Blood Cell Recognition System Using Recursive Least Square Algorithm

Puteri Suriyani, Megat Wazir and Ahmad Fauzan, Kadmin and Hamzah Asyrani, Sulaiman and Mohd Saad, Hamid and Shamsul Fakhar, Abd Gani and Norhidayah, Mohamad Yatim (2011) Blood Cell Recognition System Using Recursive Least Square Algorithm. Project Report. UTeM, Melaka, Malaysia. (Submitted)

PDF (Full Text) Blood_Cell_Recognition_System_Using_Recursive_Least_Square_Algorithm_-_Puteri_Suriyani_binti_Megat_Wazir.pdf - Submitted Version Restricted to Registered users only Download (2MB)

Abstract

A Complete Blood Count (CBC), or also known as Full Blood Count (FBC) or Full Blood Exam (FBE) or blood panel, is a test requested by a doctor or other medical professional that gives information about the cells in a patient's blood. A scientist or lab technician performs the requested testing and provides the requesting medical professional with the results of the CBC. The cells that circulate in the bloodstream are generally divided into three types: white blood cells (leukocytes), red blood cells (erythrocytes), and platelets (thrombocytes). Abnormally high or low counts may indicate the presence of many forms of disease, and hence blood counts are amongst the most commonly performed blood tests in medicine, as they can provide an overview of a patient's general health status. A CBC is routinely performed during annual physical examinations in some jurisdictions. Recursive least squares (RLS) algorithm is used in adaptive filters to find the filter coefficients that relate to recursively producing the least squares (minimum of the sum of the absolute squared) of the error signal (difference between the desired and the actual signal). This is contrast to other algorithms that aim to reduce the mean square error. The difference is that RLS filters are dependent on the signals themselves, whereas Mean Square Error (MSE) filters are dependent on their statistics (specifically, the autocorrelation of the input and the cross-correlation of the input and desired signals). If these statistics are known, an MSE filter with fixed co-efficients (i.e., independent of the incoming data) can be built. It is the goal of this project to deliver a software solution that can perform the cell blood count (CBC) diagnosis. Using statistical value of cell blood count as input, the value wi ll then be compared with normal and abnormal values by using the recursive neural network known as Recursive Least Square (RLS). The RLS will help to filter the value and provide an accurate diagnose on patient's health status. This software solution is useful to provide a quick and easy pre-screen analysis of patient's health status.

Actions (login required)

View Item